nbtree.c File Reference

#include "postgres.h"
#include "access/nbtree.h"
#include "access/relscan.h"
#include "access/xloginsert.h"
#include "commands/progress.h"
#include "commands/vacuum.h"
#include "miscadmin.h"
#include "nodes/execnodes.h"
#include "pgstat.h"
#include "storage/bulk_write.h"
#include "storage/condition_variable.h"
#include "storage/indexfsm.h"
#include "storage/ipc.h"
#include "storage/lmgr.h"
#include "storage/smgr.h"
#include "utils/fmgrprotos.h"
#include "utils/index_selfuncs.h"
#include "utils/memutils.h"

Include dependency graph for nbtree.c:

Go to the source code of this file.

Data Structures
struct	BTParallelScanDescData

Typedefs
typedef struct BTParallelScanDescData	BTParallelScanDescData
typedef struct BTParallelScanDescData *	BTParallelScanDesc

Enumerations
enum	BTPS_State {   BTPARALLEL_NOT_INITIALIZED , BTPARALLEL_NEED_PRIMSCAN , BTPARALLEL_ADVANCING , BTPARALLEL_IDLE ,   BTPARALLEL_DONE }

Functions
static void	btvacuumscan (IndexVacuumInfo *info, IndexBulkDeleteResult *stats, IndexBulkDeleteCallback callback, void *callback_state, BTCycleId cycleid)
static void	btvacuumpage (BTVacState *vstate, BlockNumber scanblkno)
static BTVacuumPosting	btreevacuumposting (BTVacState *vstate, IndexTuple posting, OffsetNumber updatedoffset, int *nremaining)
Datum	bthandler (PG_FUNCTION_ARGS)
void	btbuildempty (Relation index)
bool	btinsert (Relation rel, Datum *values, bool *isnull, ItemPointer ht_ctid, Relation heapRel, IndexUniqueCheck checkUnique, bool indexUnchanged, IndexInfo *indexInfo)
bool	btgettuple (IndexScanDesc scan, ScanDirection dir)
int64	btgetbitmap (IndexScanDesc scan, TIDBitmap *tbm)
IndexScanDesc	btbeginscan (Relation rel, int nkeys, int norderbys)
void	btrescan (IndexScanDesc scan, ScanKey scankey, int nscankeys, ScanKey orderbys, int norderbys)
void	btendscan (IndexScanDesc scan)
void	btmarkpos (IndexScanDesc scan)
void	btrestrpos (IndexScanDesc scan)
Size	btestimateparallelscan (int nkeys, int norderbys)
void	btinitparallelscan (void *target)
void	btparallelrescan (IndexScanDesc scan)
bool	_bt_parallel_seize (IndexScanDesc scan, BlockNumber *pageno, bool first)
void	_bt_parallel_release (IndexScanDesc scan, BlockNumber scan_page)
void	_bt_parallel_done (IndexScanDesc scan)
void	_bt_parallel_primscan_schedule (IndexScanDesc scan, BlockNumber prev_scan_page)
IndexBulkDeleteResult *	btbulkdelete (IndexVacuumInfo *info, IndexBulkDeleteResult *stats, IndexBulkDeleteCallback callback, void *callback_state)
IndexBulkDeleteResult *	btvacuumcleanup (IndexVacuumInfo *info, IndexBulkDeleteResult *stats)
bool	btcanreturn (Relation index, int attno)

Typedef Documentation

BTParallelScanDesc

typedef struct BTParallelScanDescData* BTParallelScanDesc

Definition at line 83 of file nbtree.c.

BTParallelScanDescData

typedef struct BTParallelScanDescData BTParallelScanDescData

Enumeration Type Documentation

BTPS_State

enum BTPS_State

Enumerator
BTPARALLEL_NOT_INITIALIZED
BTPARALLEL_NEED_PRIMSCAN
BTPARALLEL_ADVANCING
BTPARALLEL_IDLE
BTPARALLEL_DONE

Definition at line 54 of file nbtree.c.

{
    BTPARALLEL_NOT_INITIALIZED,
    BTPARALLEL_NEED_PRIMSCAN,
    BTPARALLEL_ADVANCING,
    BTPARALLEL_IDLE,
    BTPARALLEL_DONE,
} BTPS_State;

Function Documentation

_bt_parallel_done()

void _bt_parallel_done

(

IndexScanDesc

scan

)

Definition at line 732 of file nbtree.c.

{
    ParallelIndexScanDesc parallel_scan = scan->parallel_scan;
    BTParallelScanDesc btscan;
    bool        status_changed = false;
 
    /* Do nothing, for non-parallel scans */
    if (parallel_scan == NULL)
        return;
 
    btscan = (BTParallelScanDesc) OffsetToPointer((void *) parallel_scan,
                                                  parallel_scan->ps_offset);
 
    /*
     * Mark the parallel scan as done, unless some other process did so
     * already
     */
    SpinLockAcquire(&btscan->btps_mutex);
    if (btscan->btps_pageStatus != BTPARALLEL_DONE)
    {
        btscan->btps_pageStatus = BTPARALLEL_DONE;
        status_changed = true;
    }
    SpinLockRelease(&btscan->btps_mutex);
 
    /* wake up all the workers associated with this parallel scan */
    if (status_changed)
        ConditionVariableBroadcast(&btscan->btps_cv);
}

References BTPARALLEL_DONE, BTParallelScanDescData::btps_cv, BTParallelScanDescData::btps_mutex, BTParallelScanDescData::btps_pageStatus, ConditionVariableBroadcast(), OffsetToPointer, IndexScanDescData::parallel_scan, ParallelIndexScanDescData::ps_offset, SpinLockAcquire, and SpinLockRelease.

Referenced by _bt_first(), _bt_readnextpage(), and _bt_start_prim_scan().

_bt_parallel_primscan_schedule()

void _bt_parallel_primscan_schedule	(	IndexScanDesc	scan,
		BlockNumber	prev_scan_page
	)

Definition at line 771 of file nbtree.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    ParallelIndexScanDesc parallel_scan = scan->parallel_scan;
    BTParallelScanDesc btscan;
 
    Assert(so->numArrayKeys);
 
    btscan = (BTParallelScanDesc) OffsetToPointer((void *) parallel_scan,
                                                  parallel_scan->ps_offset);
 
    SpinLockAcquire(&btscan->btps_mutex);
    if (btscan->btps_scanPage == prev_scan_page &&
        btscan->btps_pageStatus == BTPARALLEL_IDLE)
    {
        btscan->btps_scanPage = InvalidBlockNumber;
        btscan->btps_pageStatus = BTPARALLEL_NEED_PRIMSCAN;
 
        /* Serialize scan's current array keys */
        for (int i = 0; i < so->numArrayKeys; i++)
        {
            BTArrayKeyInfo *array = &so->arrayKeys[i];
 
            btscan->btps_arrElems[i] = array->cur_elem;
        }
    }
    SpinLockRelease(&btscan->btps_mutex);
}

References BTScanOpaqueData::arrayKeys, Assert, BTPARALLEL_IDLE, BTPARALLEL_NEED_PRIMSCAN, BTArrayKeyInfo::cur_elem, i, InvalidBlockNumber, BTScanOpaqueData::numArrayKeys, OffsetToPointer, IndexScanDescData::opaque, IndexScanDescData::parallel_scan, SpinLockAcquire, and SpinLockRelease.

Referenced by _bt_advance_array_keys().

_bt_parallel_release()

void _bt_parallel_release	(	IndexScanDesc	scan,
		BlockNumber	scan_page
	)

Definition at line 709 of file nbtree.c.

{
    ParallelIndexScanDesc parallel_scan = scan->parallel_scan;
    BTParallelScanDesc btscan;
 
    btscan = (BTParallelScanDesc) OffsetToPointer((void *) parallel_scan,
                                                  parallel_scan->ps_offset);
 
    SpinLockAcquire(&btscan->btps_mutex);
    btscan->btps_scanPage = scan_page;
    btscan->btps_pageStatus = BTPARALLEL_IDLE;
    SpinLockRelease(&btscan->btps_mutex);
    ConditionVariableSignal(&btscan->btps_cv);
}

References BTPARALLEL_IDLE, BTParallelScanDescData::btps_cv, BTParallelScanDescData::btps_mutex, BTParallelScanDescData::btps_pageStatus, BTParallelScanDescData::btps_scanPage, ConditionVariableSignal(), OffsetToPointer, IndexScanDescData::parallel_scan, ParallelIndexScanDescData::ps_offset, SpinLockAcquire, and SpinLockRelease.

Referenced by _bt_readnextpage(), and _bt_readpage().

_bt_parallel_seize()

bool _bt_parallel_seize	(	IndexScanDesc	scan,
		BlockNumber *	pageno,
		bool	first
	)

Definition at line 605 of file nbtree.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    bool        exit_loop = false;
    bool        status = true;
    ParallelIndexScanDesc parallel_scan = scan->parallel_scan;
    BTParallelScanDesc btscan;
 
    *pageno = P_NONE;
 
    if (first)
    {
        /*
         * Initialize array related state when called from _bt_first, assuming
         * that this will either be the first primitive index scan for the
         * scan, or a previous explicitly scheduled primitive scan.
         *
         * Note: so->needPrimScan is only set when a scheduled primitive index
         * scan is set to be performed in caller's worker process.  It should
         * not be set here by us for the first primitive scan, nor should we
         * ever set it for a parallel scan that has no array keys.
         */
        so->needPrimScan = false;
        so->scanBehind = false;
    }
    else
    {
        /*
         * Don't attempt to seize the scan when backend requires another
         * primitive index scan unless we're in a position to start it now
         */
        if (so->needPrimScan)
            return false;
    }
 
    btscan = (BTParallelScanDesc) OffsetToPointer((void *) parallel_scan,
                                                  parallel_scan->ps_offset);
 
    while (1)
    {
        SpinLockAcquire(&btscan->btps_mutex);
 
        if (btscan->btps_pageStatus == BTPARALLEL_DONE)
        {
            /* We're done with this parallel index scan */
            status = false;
        }
        else if (btscan->btps_pageStatus == BTPARALLEL_NEED_PRIMSCAN)
        {
            Assert(so->numArrayKeys);
 
            /*
             * If we can start another primitive scan right away, do so.
             * Otherwise just wait.
             */
            if (first)
            {
                btscan->btps_pageStatus = BTPARALLEL_ADVANCING;
                for (int i = 0; i < so->numArrayKeys; i++)
                {
                    BTArrayKeyInfo *array = &so->arrayKeys[i];
                    ScanKey     skey = &so->keyData[array->scan_key];
 
                    array->cur_elem = btscan->btps_arrElems[i];
                    skey->sk_argument = array->elem_values[array->cur_elem];
                }
                so->needPrimScan = true;
                so->scanBehind = false;
                *pageno = InvalidBlockNumber;
                exit_loop = true;
            }
        }
        else if (btscan->btps_pageStatus != BTPARALLEL_ADVANCING)
        {
            /*
             * We have successfully seized control of the scan for the purpose
             * of advancing it to a new page!
             */
            btscan->btps_pageStatus = BTPARALLEL_ADVANCING;
            *pageno = btscan->btps_scanPage;
            exit_loop = true;
        }
        SpinLockRelease(&btscan->btps_mutex);
        if (exit_loop || !status)
            break;
        ConditionVariableSleep(&btscan->btps_cv, WAIT_EVENT_BTREE_PAGE);
    }
    ConditionVariableCancelSleep();
 
    return status;
}

References BTScanOpaqueData::arrayKeys, Assert, BTPARALLEL_ADVANCING, BTPARALLEL_DONE, BTPARALLEL_NEED_PRIMSCAN, ConditionVariableCancelSleep(), ConditionVariableSleep(), BTArrayKeyInfo::cur_elem, BTArrayKeyInfo::elem_values, i, if(), InvalidBlockNumber, BTScanOpaqueData::keyData, BTScanOpaqueData::needPrimScan, BTScanOpaqueData::numArrayKeys, OffsetToPointer, IndexScanDescData::opaque, P_NONE, IndexScanDescData::parallel_scan, BTArrayKeyInfo::scan_key, BTScanOpaqueData::scanBehind, ScanKeyData::sk_argument, SpinLockAcquire, and SpinLockRelease.

Referenced by _bt_first(), _bt_readnextpage(), and _bt_steppage().

btbeginscan()

IndexScanDesc btbeginscan	(	Relation	rel,
		int	nkeys,
		int	norderbys
	)

Definition at line 312 of file nbtree.c.

{
    IndexScanDesc scan;
    BTScanOpaque so;
 
    /* no order by operators allowed */
    Assert(norderbys == 0);
 
    /* get the scan */
    scan = RelationGetIndexScan(rel, nkeys, norderbys);
 
    /* allocate private workspace */
    so = (BTScanOpaque) palloc(sizeof(BTScanOpaqueData));
    BTScanPosInvalidate(so->currPos);
    BTScanPosInvalidate(so->markPos);
    if (scan->numberOfKeys > 0)
        so->keyData = (ScanKey) palloc(scan->numberOfKeys * sizeof(ScanKeyData));
    else
        so->keyData = NULL;
 
    so->needPrimScan = false;
    so->scanBehind = false;
    so->arrayKeys = NULL;
    so->orderProcs = NULL;
    so->arrayContext = NULL;
 
    so->killedItems = NULL;     /* until needed */
    so->numKilled = 0;
 
    /*
     * We don't know yet whether the scan will be index-only, so we do not
     * allocate the tuple workspace arrays until btrescan.  However, we set up
     * scan->xs_itupdesc whether we'll need it or not, since that's so cheap.
     */
    so->currTuples = so->markTuples = NULL;
 
    scan->xs_itupdesc = RelationGetDescr(rel);
 
    scan->opaque = so;
 
    return scan;
}

References BTScanOpaqueData::arrayContext, BTScanOpaqueData::arrayKeys, Assert, BTScanPosInvalidate, BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, BTScanOpaqueData::keyData, BTScanOpaqueData::killedItems, BTScanOpaqueData::markPos, BTScanOpaqueData::markTuples, BTScanOpaqueData::needPrimScan, IndexScanDescData::numberOfKeys, BTScanOpaqueData::numKilled, IndexScanDescData::opaque, BTScanOpaqueData::orderProcs, palloc(), RelationGetDescr, RelationGetIndexScan(), BTScanOpaqueData::scanBehind, and IndexScanDescData::xs_itupdesc.

Referenced by bthandler().

btbuildempty()

void btbuildempty

(

Relation

index

)

Definition at line 159 of file nbtree.c.

{
    bool        allequalimage = _bt_allequalimage(index, false);
    BulkWriteState *bulkstate;
    BulkWriteBuffer metabuf;
 
    bulkstate = smgr_bulk_start_rel(index, INIT_FORKNUM);
 
    /* Construct metapage. */
    metabuf = smgr_bulk_get_buf(bulkstate);
    _bt_initmetapage((Page) metabuf, P_NONE, 0, allequalimage);
    smgr_bulk_write(bulkstate, BTREE_METAPAGE, metabuf, true);
 
    smgr_bulk_finish(bulkstate);
}

References _bt_allequalimage(), _bt_initmetapage(), BTREE_METAPAGE, INIT_FORKNUM, P_NONE, smgr_bulk_finish(), smgr_bulk_get_buf(), smgr_bulk_start_rel(), and smgr_bulk_write().

Referenced by bthandler().

btbulkdelete()

IndexBulkDeleteResult* btbulkdelete	(	IndexVacuumInfo *	info,
		IndexBulkDeleteResult *	stats,
		IndexBulkDeleteCallback	callback,
		void *	callback_state
	)

Definition at line 808 of file nbtree.c.

{
    Relation    rel = info->index;
    BTCycleId   cycleid;
 
    /* allocate stats if first time through, else re-use existing struct */
    if (stats == NULL)
        stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
 
    /* Establish the vacuum cycle ID to use for this scan */
    /* The ENSURE stuff ensures we clean up shared memory on failure */
    PG_ENSURE_ERROR_CLEANUP(_bt_end_vacuum_callback, PointerGetDatum(rel));
    {
        cycleid = _bt_start_vacuum(rel);
 
        btvacuumscan(info, stats, callback, callback_state, cycleid);
    }
    PG_END_ENSURE_ERROR_CLEANUP(_bt_end_vacuum_callback, PointerGetDatum(rel));
    _bt_end_vacuum(rel);
 
    return stats;
}

References _bt_end_vacuum(), _bt_end_vacuum_callback(), _bt_start_vacuum(), btvacuumscan(), callback(), IndexVacuumInfo::index, palloc0(), PG_END_ENSURE_ERROR_CLEANUP, PG_ENSURE_ERROR_CLEANUP, and PointerGetDatum().

Referenced by bthandler().

btcanreturn()

bool btcanreturn	(	Relation	index,
		int	attno
	)

Definition at line 1444 of file nbtree.c.

{
    return true;
}

Referenced by bthandler().

btendscan()

void btendscan

(

IndexScanDesc

scan

)

Definition at line 417 of file nbtree.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
 
    /* we aren't holding any read locks, but gotta drop the pins */
    if (BTScanPosIsValid(so->currPos))
    {
        /* Before leaving current page, deal with any killed items */
        if (so->numKilled > 0)
            _bt_killitems(scan);
        BTScanPosUnpinIfPinned(so->currPos);
    }
 
    so->markItemIndex = -1;
    BTScanPosUnpinIfPinned(so->markPos);
 
    /* No need to invalidate positions, the RAM is about to be freed. */
 
    /* Release storage */
    if (so->keyData != NULL)
        pfree(so->keyData);
    /* so->arrayKeys and so->orderProcs are in arrayContext */
    if (so->arrayContext != NULL)
        MemoryContextDelete(so->arrayContext);
    if (so->killedItems != NULL)
        pfree(so->killedItems);
    if (so->currTuples != NULL)
        pfree(so->currTuples);
    /* so->markTuples should not be pfree'd, see btrescan */
    pfree(so);
}

References _bt_killitems(), BTScanOpaqueData::arrayContext, BTScanPosIsValid, BTScanPosUnpinIfPinned, BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, if(), BTScanOpaqueData::keyData, BTScanOpaqueData::killedItems, BTScanOpaqueData::markItemIndex, BTScanOpaqueData::markPos, MemoryContextDelete(), BTScanOpaqueData::numKilled, IndexScanDescData::opaque, and pfree().

Referenced by bthandler().

btestimateparallelscan()

Size btestimateparallelscan	(	int	nkeys,
		int	norderbys
	)

Definition at line 537 of file nbtree.c.

{
    /* Pessimistically assume all input scankeys will be output with arrays */
    return offsetof(BTParallelScanDescData, btps_arrElems) + sizeof(int) * nkeys;
}

References BTParallelScanDescData::btps_arrElems.

Referenced by bthandler().

btgetbitmap()

int64 btgetbitmap	(	IndexScanDesc	scan,
		TIDBitmap *	tbm
	)

Definition at line 266 of file nbtree.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    int64       ntids = 0;
    ItemPointer heapTid;
 
    /* Each loop iteration performs another primitive index scan */
    do
    {
        /* Fetch the first page & tuple */
        if (_bt_first(scan, ForwardScanDirection))
        {
            /* Save tuple ID, and continue scanning */
            heapTid = &scan->xs_heaptid;
            tbm_add_tuples(tbm, heapTid, 1, false);
            ntids++;
 
            for (;;)
            {
                /*
                 * Advance to next tuple within page.  This is the same as the
                 * easy case in _bt_next().
                 */
                if (++so->currPos.itemIndex > so->currPos.lastItem)
                {
                    /* let _bt_next do the heavy lifting */
                    if (!_bt_next(scan, ForwardScanDirection))
                        break;
                }
 
                /* Save tuple ID, and continue scanning */
                heapTid = &so->currPos.items[so->currPos.itemIndex].heapTid;
                tbm_add_tuples(tbm, heapTid, 1, false);
                ntids++;
            }
        }
        /* Now see if we need another primitive index scan */
    } while (so->numArrayKeys && _bt_start_prim_scan(scan, ForwardScanDirection));
 
    return ntids;
}

References _bt_first(), _bt_next(), BTScanOpaqueData::currPos, ForwardScanDirection, BTScanPosItem::heapTid, if(), BTScanPosData::itemIndex, BTScanPosData::items, BTScanPosData::lastItem, IndexScanDescData::opaque, tbm_add_tuples(), and IndexScanDescData::xs_heaptid.

Referenced by bthandler().

btgettuple()

bool btgettuple	(	IndexScanDesc	scan,
		ScanDirection	dir
	)

Definition at line 206 of file nbtree.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    bool        res;
 
    /* btree indexes are never lossy */
    scan->xs_recheck = false;
 
    /* Each loop iteration performs another primitive index scan */
    do
    {
        /*
         * If we've already initialized this scan, we can just advance it in
         * the appropriate direction.  If we haven't done so yet, we call
         * _bt_first() to get the first item in the scan.
         */
        if (!BTScanPosIsValid(so->currPos))
            res = _bt_first(scan, dir);
        else
        {
            /*
             * Check to see if we should kill the previously-fetched tuple.
             */
            if (scan->kill_prior_tuple)
            {
                /*
                 * Yes, remember it for later. (We'll deal with all such
                 * tuples at once right before leaving the index page.)  The
                 * test for numKilled overrun is not just paranoia: if the
                 * caller reverses direction in the indexscan then the same
                 * item might get entered multiple times. It's not worth
                 * trying to optimize that, so we don't detect it, but instead
                 * just forget any excess entries.
                 */
                if (so->killedItems == NULL)
                    so->killedItems = (int *)
                        palloc(MaxTIDsPerBTreePage * sizeof(int));
                if (so->numKilled < MaxTIDsPerBTreePage)
                    so->killedItems[so->numKilled++] = so->currPos.itemIndex;
            }
 
            /*
             * Now continue the scan.
             */
            res = _bt_next(scan, dir);
        }
 
        /* If we have a tuple, return it ... */
        if (res)
            break;
        /* ... otherwise see if we need another primitive index scan */
    } while (so->numArrayKeys && _bt_start_prim_scan(scan, dir));
 
    return res;
}

References _bt_first(), _bt_next(), BTScanPosIsValid, BTScanOpaqueData::currPos, if(), BTScanPosData::itemIndex, IndexScanDescData::kill_prior_tuple, BTScanOpaqueData::killedItems, MaxTIDsPerBTreePage, BTScanOpaqueData::numKilled, IndexScanDescData::opaque, palloc(), res, and IndexScanDescData::xs_recheck.

Referenced by bthandler().

bthandler()

Datum bthandler

(

PG_FUNCTION_ARGS

)

Definition at line 101 of file nbtree.c.

{
    IndexAmRoutine *amroutine = makeNode(IndexAmRoutine);
 
    amroutine->amstrategies = BTMaxStrategyNumber;
    amroutine->amsupport = BTNProcs;
    amroutine->amoptsprocnum = BTOPTIONS_PROC;
    amroutine->amcanorder = true;
    amroutine->amcanorderbyop = false;
    amroutine->amcanbackward = true;
    amroutine->amcanunique = true;
    amroutine->amcanmulticol = true;
    amroutine->amoptionalkey = true;
    amroutine->amsearcharray = true;
    amroutine->amsearchnulls = true;
    amroutine->amstorage = false;
    amroutine->amclusterable = true;
    amroutine->ampredlocks = true;
    amroutine->amcanparallel = true;
    amroutine->amcanbuildparallel = true;
    amroutine->amcaninclude = true;
    amroutine->amusemaintenanceworkmem = false;
    amroutine->amsummarizing = false;
    amroutine->amparallelvacuumoptions =
        VACUUM_OPTION_PARALLEL_BULKDEL | VACUUM_OPTION_PARALLEL_COND_CLEANUP;
    amroutine->amkeytype = InvalidOid;
 
    amroutine->ambuild = btbuild;
    amroutine->ambuildempty = btbuildempty;
    amroutine->aminsert = btinsert;
    amroutine->aminsertcleanup = NULL;
    amroutine->ambulkdelete = btbulkdelete;
    amroutine->amvacuumcleanup = btvacuumcleanup;
    amroutine->amcanreturn = btcanreturn;
    amroutine->amcostestimate = btcostestimate;
    amroutine->amoptions = btoptions;
    amroutine->amproperty = btproperty;
    amroutine->ambuildphasename = btbuildphasename;
    amroutine->amvalidate = btvalidate;
    amroutine->amadjustmembers = btadjustmembers;
    amroutine->ambeginscan = btbeginscan;
    amroutine->amrescan = btrescan;
    amroutine->amgettuple = btgettuple;
    amroutine->amgetbitmap = btgetbitmap;
    amroutine->amendscan = btendscan;
    amroutine->ammarkpos = btmarkpos;
    amroutine->amrestrpos = btrestrpos;
    amroutine->amestimateparallelscan = btestimateparallelscan;
    amroutine->aminitparallelscan = btinitparallelscan;
    amroutine->amparallelrescan = btparallelrescan;
 
    PG_RETURN_POINTER(amroutine);
}

References IndexAmRoutine::amadjustmembers, IndexAmRoutine::ambeginscan, IndexAmRoutine::ambuild, IndexAmRoutine::ambuildempty, IndexAmRoutine::ambuildphasename, IndexAmRoutine::ambulkdelete, IndexAmRoutine::amcanbackward, IndexAmRoutine::amcanbuildparallel, IndexAmRoutine::amcaninclude, IndexAmRoutine::amcanmulticol, IndexAmRoutine::amcanorder, IndexAmRoutine::amcanorderbyop, IndexAmRoutine::amcanparallel, IndexAmRoutine::amcanreturn, IndexAmRoutine::amcanunique, IndexAmRoutine::amclusterable, IndexAmRoutine::amcostestimate, IndexAmRoutine::amendscan, IndexAmRoutine::amestimateparallelscan, IndexAmRoutine::amgetbitmap, IndexAmRoutine::amgettuple, IndexAmRoutine::aminitparallelscan, IndexAmRoutine::aminsert, IndexAmRoutine::aminsertcleanup, IndexAmRoutine::amkeytype, IndexAmRoutine::ammarkpos, IndexAmRoutine::amoptionalkey, IndexAmRoutine::amoptions, IndexAmRoutine::amoptsprocnum, IndexAmRoutine::amparallelrescan, IndexAmRoutine::amparallelvacuumoptions, IndexAmRoutine::ampredlocks, IndexAmRoutine::amproperty, IndexAmRoutine::amrescan, IndexAmRoutine::amrestrpos, IndexAmRoutine::amsearcharray, IndexAmRoutine::amsearchnulls, IndexAmRoutine::amstorage, IndexAmRoutine::amstrategies, IndexAmRoutine::amsummarizing, IndexAmRoutine::amsupport, IndexAmRoutine::amusemaintenanceworkmem, IndexAmRoutine::amvacuumcleanup, IndexAmRoutine::amvalidate, btadjustmembers(), btbeginscan(), btbuild(), btbuildempty(), btbuildphasename(), btbulkdelete(), btcanreturn(), btcostestimate(), btendscan(), btestimateparallelscan(), btgetbitmap(), btgettuple(), btinitparallelscan(), btinsert(), btmarkpos(), BTMaxStrategyNumber, BTNProcs, btoptions(), BTOPTIONS_PROC, btparallelrescan(), btproperty(), btrescan(), btrestrpos(), btvacuumcleanup(), btvalidate(), InvalidOid, makeNode, PG_RETURN_POINTER, VACUUM_OPTION_PARALLEL_BULKDEL, and VACUUM_OPTION_PARALLEL_COND_CLEANUP.

btinitparallelscan()

void btinitparallelscan

(

void *

target

)

Definition at line 547 of file nbtree.c.

{
    BTParallelScanDesc bt_target = (BTParallelScanDesc) target;
 
    SpinLockInit(&bt_target->btps_mutex);
    bt_target->btps_scanPage = InvalidBlockNumber;
    bt_target->btps_pageStatus = BTPARALLEL_NOT_INITIALIZED;
    ConditionVariableInit(&bt_target->btps_cv);
}

References BTPARALLEL_NOT_INITIALIZED, BTParallelScanDescData::btps_cv, BTParallelScanDescData::btps_mutex, BTParallelScanDescData::btps_pageStatus, BTParallelScanDescData::btps_scanPage, ConditionVariableInit(), InvalidBlockNumber, and SpinLockInit.

Referenced by bthandler().

btinsert()

bool btinsert	(	Relation	rel,
		Datum *	values,
		bool *	isnull,
		ItemPointer	ht_ctid,
		Relation	heapRel,
		IndexUniqueCheck	checkUnique,
		bool	indexUnchanged,
		IndexInfo *	indexInfo
	)

Definition at line 182 of file nbtree.c.

{
    bool        result;
    IndexTuple  itup;
 
    /* generate an index tuple */
    itup = index_form_tuple(RelationGetDescr(rel), values, isnull);
    itup->t_tid = *ht_ctid;
 
    result = _bt_doinsert(rel, itup, checkUnique, indexUnchanged, heapRel);
 
    pfree(itup);
 
    return result;
}

References _bt_doinsert(), index_form_tuple(), pfree(), RelationGetDescr, IndexTupleData::t_tid, and values.

Referenced by bthandler().

btmarkpos()

void btmarkpos

(

IndexScanDesc

scan

)

Definition at line 453 of file nbtree.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
 
    /* There may be an old mark with a pin (but no lock). */
    BTScanPosUnpinIfPinned(so->markPos);
 
    /*
     * Just record the current itemIndex.  If we later step to next page
     * before releasing the marked position, _bt_steppage makes a full copy of
     * the currPos struct in markPos.  If (as often happens) the mark is moved
     * before we leave the page, we don't have to do that work.
     */
    if (BTScanPosIsValid(so->currPos))
        so->markItemIndex = so->currPos.itemIndex;
    else
    {
        BTScanPosInvalidate(so->markPos);
        so->markItemIndex = -1;
    }
}

References BTScanPosInvalidate, BTScanPosIsValid, BTScanPosUnpinIfPinned, BTScanOpaqueData::currPos, BTScanPosData::itemIndex, BTScanOpaqueData::markItemIndex, BTScanOpaqueData::markPos, and IndexScanDescData::opaque.

Referenced by bthandler().

btparallelrescan()

void btparallelrescan

(

IndexScanDesc

scan

)

Definition at line 561 of file nbtree.c.

{
    BTParallelScanDesc btscan;
    ParallelIndexScanDesc parallel_scan = scan->parallel_scan;
 
    Assert(parallel_scan);
 
    btscan = (BTParallelScanDesc) OffsetToPointer((void *) parallel_scan,
                                                  parallel_scan->ps_offset);
 
    /*
     * In theory, we don't need to acquire the spinlock here, because there
     * shouldn't be any other workers running at this point, but we do so for
     * consistency.
     */
    SpinLockAcquire(&btscan->btps_mutex);
    btscan->btps_scanPage = InvalidBlockNumber;
    btscan->btps_pageStatus = BTPARALLEL_NOT_INITIALIZED;
    SpinLockRelease(&btscan->btps_mutex);
}

References Assert, BTPARALLEL_NOT_INITIALIZED, BTParallelScanDescData::btps_mutex, BTParallelScanDescData::btps_pageStatus, BTParallelScanDescData::btps_scanPage, InvalidBlockNumber, OffsetToPointer, IndexScanDescData::parallel_scan, ParallelIndexScanDescData::ps_offset, SpinLockAcquire, and SpinLockRelease.

Referenced by bthandler().

btreevacuumposting()

static BTVacuumPosting btreevacuumposting ( BTVacState *  vstate, IndexTuple  posting, OffsetNumber  updatedoffset, int *  nremaining  )

static

Definition at line 1395 of file nbtree.c.

{
    int         live = 0;
    int         nitem = BTreeTupleGetNPosting(posting);
    ItemPointer items = BTreeTupleGetPosting(posting);
    BTVacuumPosting vacposting = NULL;
 
    for (int i = 0; i < nitem; i++)
    {
        if (!vstate->callback(items + i, vstate->callback_state))
        {
            /* Live table TID */
            live++;
        }
        else if (vacposting == NULL)
        {
            /*
             * First dead table TID encountered.
             *
             * It's now clear that we need to delete one or more dead table
             * TIDs, so start maintaining metadata describing how to update
             * existing posting list tuple.
             */
            vacposting = palloc(offsetof(BTVacuumPostingData, deletetids) +
                                nitem * sizeof(uint16));
 
            vacposting->itup = posting;
            vacposting->updatedoffset = updatedoffset;
            vacposting->ndeletedtids = 0;
            vacposting->deletetids[vacposting->ndeletedtids++] = i;
        }
        else
        {
            /* Second or subsequent dead table TID */
            vacposting->deletetids[vacposting->ndeletedtids++] = i;
        }
    }
 
    *nremaining = live;
    return vacposting;
}

References BTreeTupleGetNPosting(), BTreeTupleGetPosting(), BTVacState::callback, BTVacState::callback_state, BTVacuumPostingData::deletetids, i, items, BTVacuumPostingData::itup, BTVacuumPostingData::ndeletedtids, palloc(), and BTVacuumPostingData::updatedoffset.

Referenced by btvacuumpage().

btrescan()

void btrescan	(	IndexScanDesc	scan,
		ScanKey	scankey,
		int	nscankeys,
		ScanKey	orderbys,
		int	norderbys
	)

Definition at line 359 of file nbtree.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
 
    /* we aren't holding any read locks, but gotta drop the pins */
    if (BTScanPosIsValid(so->currPos))
    {
        /* Before leaving current page, deal with any killed items */
        if (so->numKilled > 0)
            _bt_killitems(scan);
        BTScanPosUnpinIfPinned(so->currPos);
        BTScanPosInvalidate(so->currPos);
    }
 
    so->markItemIndex = -1;
    so->needPrimScan = false;
    so->scanBehind = false;
    BTScanPosUnpinIfPinned(so->markPos);
    BTScanPosInvalidate(so->markPos);
 
    /*
     * Allocate tuple workspace arrays, if needed for an index-only scan and
     * not already done in a previous rescan call.  To save on palloc
     * overhead, both workspaces are allocated as one palloc block; only this
     * function and btendscan know that.
     *
     * NOTE: this data structure also makes it safe to return data from a
     * "name" column, even though btree name_ops uses an underlying storage
     * datatype of cstring.  The risk there is that "name" is supposed to be
     * padded to NAMEDATALEN, but the actual index tuple is probably shorter.
     * However, since we only return data out of tuples sitting in the
     * currTuples array, a fetch of NAMEDATALEN bytes can at worst pull some
     * data out of the markTuples array --- running off the end of memory for
     * a SIGSEGV is not possible.  Yeah, this is ugly as sin, but it beats
     * adding special-case treatment for name_ops elsewhere.
     */
    if (scan->xs_want_itup && so->currTuples == NULL)
    {
        so->currTuples = (char *) palloc(BLCKSZ * 2);
        so->markTuples = so->currTuples + BLCKSZ;
    }
 
    /*
     * Reset the scan keys
     */
    if (scankey && scan->numberOfKeys > 0)
        memmove(scan->keyData,
                scankey,
                scan->numberOfKeys * sizeof(ScanKeyData));
    so->numberOfKeys = 0;       /* until _bt_preprocess_keys sets it */
    so->numArrayKeys = 0;       /* ditto */
}

References _bt_killitems(), BTScanPosInvalidate, BTScanPosIsValid, BTScanPosUnpinIfPinned, BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, if(), IndexScanDescData::keyData, BTScanOpaqueData::markItemIndex, BTScanOpaqueData::markPos, BTScanOpaqueData::markTuples, BTScanOpaqueData::needPrimScan, BTScanOpaqueData::numArrayKeys, BTScanOpaqueData::numberOfKeys, IndexScanDescData::numberOfKeys, BTScanOpaqueData::numKilled, IndexScanDescData::opaque, palloc(), BTScanOpaqueData::scanBehind, and IndexScanDescData::xs_want_itup.

Referenced by bthandler().

btrestrpos()

void btrestrpos

(

IndexScanDesc

scan

)

Definition at line 479 of file nbtree.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
 
    if (so->markItemIndex >= 0)
    {
        /*
         * The scan has never moved to a new page since the last mark.  Just
         * restore the itemIndex.
         *
         * NB: In this case we can't count on anything in so->markPos to be
         * accurate.
         */
        so->currPos.itemIndex = so->markItemIndex;
    }
    else
    {
        /*
         * The scan moved to a new page after last mark or restore, and we are
         * now restoring to the marked page.  We aren't holding any read
         * locks, but if we're still holding the pin for the current position,
         * we must drop it.
         */
        if (BTScanPosIsValid(so->currPos))
        {
            /* Before leaving current page, deal with any killed items */
            if (so->numKilled > 0)
                _bt_killitems(scan);
            BTScanPosUnpinIfPinned(so->currPos);
        }
 
        if (BTScanPosIsValid(so->markPos))
        {
            /* bump pin on mark buffer for assignment to current buffer */
            if (BTScanPosIsPinned(so->markPos))
                IncrBufferRefCount(so->markPos.buf);
            memcpy(&so->currPos, &so->markPos,
                   offsetof(BTScanPosData, items[1]) +
                   so->markPos.lastItem * sizeof(BTScanPosItem));
            if (so->currTuples)
                memcpy(so->currTuples, so->markTuples,
                       so->markPos.nextTupleOffset);
            /* Reset the scan's array keys (see _bt_steppage for why) */
            if (so->numArrayKeys)
            {
                _bt_start_array_keys(scan, so->currPos.dir);
                so->needPrimScan = false;
            }
        }
        else
            BTScanPosInvalidate(so->currPos);
    }
}

References _bt_killitems(), _bt_start_array_keys(), BTScanPosInvalidate, BTScanPosIsPinned, BTScanPosIsValid, BTScanPosUnpinIfPinned, BTScanPosData::buf, BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, BTScanPosData::dir, if(), IncrBufferRefCount(), BTScanPosData::itemIndex, items, BTScanPosData::lastItem, BTScanOpaqueData::markItemIndex, BTScanOpaqueData::markPos, BTScanOpaqueData::markTuples, BTScanOpaqueData::needPrimScan, BTScanPosData::nextTupleOffset, BTScanOpaqueData::numArrayKeys, BTScanOpaqueData::numKilled, and IndexScanDescData::opaque.

Referenced by bthandler().

btvacuumcleanup()

IndexBulkDeleteResult* btvacuumcleanup	(	IndexVacuumInfo *	info,
		IndexBulkDeleteResult *	stats
	)

Definition at line 838 of file nbtree.c.

{
    BlockNumber num_delpages;
 
    /* No-op in ANALYZE ONLY mode */
    if (info->analyze_only)
        return stats;
 
    /*
     * If btbulkdelete was called, we need not do anything (we just maintain
     * the information used within _bt_vacuum_needs_cleanup() by calling
     * _bt_set_cleanup_info() below).
     *
     * If btbulkdelete was _not_ called, then we have a choice to make: we
     * must decide whether or not a btvacuumscan() call is needed now (i.e.
     * whether the ongoing VACUUM operation can entirely avoid a physical scan
     * of the index).  A call to _bt_vacuum_needs_cleanup() decides it for us
     * now.
     */
    if (stats == NULL)
    {
        /* Check if VACUUM operation can entirely avoid btvacuumscan() call */
        if (!_bt_vacuum_needs_cleanup(info->index))
            return NULL;
 
        /*
         * Since we aren't going to actually delete any leaf items, there's no
         * need to go through all the vacuum-cycle-ID pushups here.
         *
         * Posting list tuples are a source of inaccuracy for cleanup-only
         * scans.  btvacuumscan() will assume that the number of index tuples
         * from each page can be used as num_index_tuples, even though
         * num_index_tuples is supposed to represent the number of TIDs in the
         * index.  This naive approach can underestimate the number of tuples
         * in the index significantly.
         *
         * We handle the problem by making num_index_tuples an estimate in
         * cleanup-only case.
         */
        stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
        btvacuumscan(info, stats, NULL, NULL, 0);
        stats->estimated_count = true;
    }
 
    /*
     * Maintain num_delpages value in metapage for _bt_vacuum_needs_cleanup().
     *
     * num_delpages is the number of deleted pages now in the index that were
     * not safe to place in the FSM to be recycled just yet.  num_delpages is
     * greater than 0 only when _bt_pagedel() actually deleted pages during
     * our call to btvacuumscan().  Even then, _bt_pendingfsm_finalize() must
     * have failed to place any newly deleted pages in the FSM just moments
     * ago.  (Actually, there are edge cases where recycling of the current
     * VACUUM's newly deleted pages does not even become safe by the time the
     * next VACUUM comes around.  See nbtree/README.)
     */
    Assert(stats->pages_deleted >= stats->pages_free);
    num_delpages = stats->pages_deleted - stats->pages_free;
    _bt_set_cleanup_info(info->index, num_delpages);
 
    /*
     * It's quite possible for us to be fooled by concurrent page splits into
     * double-counting some index tuples, so disbelieve any total that exceeds
     * the underlying heap's count ... if we know that accurately.  Otherwise
     * this might just make matters worse.
     */
    if (!info->estimated_count)
    {
        if (stats->num_index_tuples > info->num_heap_tuples)
            stats->num_index_tuples = info->num_heap_tuples;
    }
 
    return stats;
}

References _bt_set_cleanup_info(), _bt_vacuum_needs_cleanup(), IndexVacuumInfo::analyze_only, Assert, btvacuumscan(), IndexVacuumInfo::estimated_count, IndexBulkDeleteResult::estimated_count, IndexVacuumInfo::index, IndexVacuumInfo::num_heap_tuples, IndexBulkDeleteResult::num_index_tuples, IndexBulkDeleteResult::pages_deleted, IndexBulkDeleteResult::pages_free, and palloc0().

Referenced by bthandler().

btvacuumpage()

static void btvacuumpage ( BTVacState *  vstate, BlockNumber  scanblkno  )

static

Definition at line 1060 of file nbtree.c.

{
    IndexVacuumInfo *info = vstate->info;
    IndexBulkDeleteResult *stats = vstate->stats;
    IndexBulkDeleteCallback callback = vstate->callback;
    void       *callback_state = vstate->callback_state;
    Relation    rel = info->index;
    Relation    heaprel = info->heaprel;
    bool        attempt_pagedel;
    BlockNumber blkno,
                backtrack_to;
    Buffer      buf;
    Page        page;
    BTPageOpaque opaque;
 
    blkno = scanblkno;
 
backtrack:
 
    attempt_pagedel = false;
    backtrack_to = P_NONE;
 
    /* call vacuum_delay_point while not holding any buffer lock */
    vacuum_delay_point();
 
    /*
     * We can't use _bt_getbuf() here because it always applies
     * _bt_checkpage(), which will barf on an all-zero page. We want to
     * recycle all-zero pages, not fail.  Also, we want to use a nondefault
     * buffer access strategy.
     */
    buf = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
                             info->strategy);
    _bt_lockbuf(rel, buf, BT_READ);
    page = BufferGetPage(buf);
    opaque = NULL;
    if (!PageIsNew(page))
    {
        _bt_checkpage(rel, buf);
        opaque = BTPageGetOpaque(page);
    }
 
    Assert(blkno <= scanblkno);
    if (blkno != scanblkno)
    {
        /*
         * We're backtracking.
         *
         * We followed a right link to a sibling leaf page (a page that
         * happens to be from a block located before scanblkno).  The only
         * case we want to do anything with is a live leaf page having the
         * current vacuum cycle ID.
         *
         * The page had better be in a state that's consistent with what we
         * expect.  Check for conditions that imply corruption in passing.  It
         * can't be half-dead because only an interrupted VACUUM process can
         * leave pages in that state, so we'd definitely have dealt with it
         * back when the page was the scanblkno page (half-dead pages are
         * always marked fully deleted by _bt_pagedel(), barring corruption).
         */
        if (!opaque || !P_ISLEAF(opaque) || P_ISHALFDEAD(opaque))
        {
            Assert(false);
            ereport(LOG,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg_internal("right sibling %u of scanblkno %u unexpectedly in an inconsistent state in index \"%s\"",
                                     blkno, scanblkno, RelationGetRelationName(rel))));
            _bt_relbuf(rel, buf);
            return;
        }
 
        /*
         * We may have already processed the page in an earlier call, when the
         * page was scanblkno.  This happens when the leaf page split occurred
         * after the scan began, but before the right sibling page became the
         * scanblkno.
         *
         * Page may also have been deleted by current btvacuumpage() call,
         * since _bt_pagedel() sometimes deletes the right sibling page of
         * scanblkno in passing (it does so after we decided where to
         * backtrack to).  We don't need to process this page as a deleted
         * page a second time now (in fact, it would be wrong to count it as a
         * deleted page in the bulk delete statistics a second time).
         */
        if (opaque->btpo_cycleid != vstate->cycleid || P_ISDELETED(opaque))
        {
            /* Done with current scanblkno (and all lower split pages) */
            _bt_relbuf(rel, buf);
            return;
        }
    }
 
    if (!opaque || BTPageIsRecyclable(page, heaprel))
    {
        /* Okay to recycle this page (which could be leaf or internal) */
        RecordFreeIndexPage(rel, blkno);
        stats->pages_deleted++;
        stats->pages_free++;
    }
    else if (P_ISDELETED(opaque))
    {
        /*
         * Already deleted page (which could be leaf or internal).  Can't
         * recycle yet.
         */
        stats->pages_deleted++;
    }
    else if (P_ISHALFDEAD(opaque))
    {
        /* Half-dead leaf page (from interrupted VACUUM) -- finish deleting */
        attempt_pagedel = true;
 
        /*
         * _bt_pagedel() will increment both pages_newly_deleted and
         * pages_deleted stats in all cases (barring corruption)
         */
    }
    else if (P_ISLEAF(opaque))
    {
        OffsetNumber deletable[MaxIndexTuplesPerPage];
        int         ndeletable;
        BTVacuumPosting updatable[MaxIndexTuplesPerPage];
        int         nupdatable;
        OffsetNumber offnum,
                    minoff,
                    maxoff;
        int         nhtidsdead,
                    nhtidslive;
 
        /*
         * Trade in the initial read lock for a full cleanup lock on this
         * page.  We must get such a lock on every leaf page over the course
         * of the vacuum scan, whether or not it actually contains any
         * deletable tuples --- see nbtree/README.
         */
        _bt_upgradelockbufcleanup(rel, buf);
 
        /*
         * Check whether we need to backtrack to earlier pages.  What we are
         * concerned about is a page split that happened since we started the
         * vacuum scan.  If the split moved tuples on the right half of the
         * split (i.e. the tuples that sort high) to a block that we already
         * passed over, then we might have missed the tuples.  We need to
         * backtrack now.  (Must do this before possibly clearing btpo_cycleid
         * or deleting scanblkno page below!)
         */
        if (vstate->cycleid != 0 &&
            opaque->btpo_cycleid == vstate->cycleid &&
            !(opaque->btpo_flags & BTP_SPLIT_END) &&
            !P_RIGHTMOST(opaque) &&
            opaque->btpo_next < scanblkno)
            backtrack_to = opaque->btpo_next;
 
        ndeletable = 0;
        nupdatable = 0;
        minoff = P_FIRSTDATAKEY(opaque);
        maxoff = PageGetMaxOffsetNumber(page);
        nhtidsdead = 0;
        nhtidslive = 0;
        if (callback)
        {
            /* btbulkdelete callback tells us what to delete (or update) */
            for (offnum = minoff;
                 offnum <= maxoff;
                 offnum = OffsetNumberNext(offnum))
            {
                IndexTuple  itup;
 
                itup = (IndexTuple) PageGetItem(page,
                                                PageGetItemId(page, offnum));
 
                Assert(!BTreeTupleIsPivot(itup));
                if (!BTreeTupleIsPosting(itup))
                {
                    /* Regular tuple, standard table TID representation */
                    if (callback(&itup->t_tid, callback_state))
                    {
                        deletable[ndeletable++] = offnum;
                        nhtidsdead++;
                    }
                    else
                        nhtidslive++;
                }
                else
                {
                    BTVacuumPosting vacposting;
                    int         nremaining;
 
                    /* Posting list tuple */
                    vacposting = btreevacuumposting(vstate, itup, offnum,
                                                    &nremaining);
                    if (vacposting == NULL)
                    {
                        /*
                         * All table TIDs from the posting tuple remain, so no
                         * delete or update required
                         */
                        Assert(nremaining == BTreeTupleGetNPosting(itup));
                    }
                    else if (nremaining > 0)
                    {
 
                        /*
                         * Store metadata about posting list tuple in
                         * updatable array for entire page.  Existing tuple
                         * will be updated during the later call to
                         * _bt_delitems_vacuum().
                         */
                        Assert(nremaining < BTreeTupleGetNPosting(itup));
                        updatable[nupdatable++] = vacposting;
                        nhtidsdead += BTreeTupleGetNPosting(itup) - nremaining;
                    }
                    else
                    {
                        /*
                         * All table TIDs from the posting list must be
                         * deleted.  We'll delete the index tuple completely
                         * (no update required).
                         */
                        Assert(nremaining == 0);
                        deletable[ndeletable++] = offnum;
                        nhtidsdead += BTreeTupleGetNPosting(itup);
                        pfree(vacposting);
                    }
 
                    nhtidslive += nremaining;
                }
            }
        }
 
        /*
         * Apply any needed deletes or updates.  We issue just one
         * _bt_delitems_vacuum() call per page, so as to minimize WAL traffic.
         */
        if (ndeletable > 0 || nupdatable > 0)
        {
            Assert(nhtidsdead >= ndeletable + nupdatable);
            _bt_delitems_vacuum(rel, buf, deletable, ndeletable, updatable,
                                nupdatable);
 
            stats->tuples_removed += nhtidsdead;
            /* must recompute maxoff */
            maxoff = PageGetMaxOffsetNumber(page);
 
            /* can't leak memory here */
            for (int i = 0; i < nupdatable; i++)
                pfree(updatable[i]);
        }
        else
        {
            /*
             * If the leaf page has been split during this vacuum cycle, it
             * seems worth expending a write to clear btpo_cycleid even if we
             * don't have any deletions to do.  (If we do, _bt_delitems_vacuum
             * takes care of this.)  This ensures we won't process the page
             * again.
             *
             * We treat this like a hint-bit update because there's no need to
             * WAL-log it.
             */
            Assert(nhtidsdead == 0);
            if (vstate->cycleid != 0 &&
                opaque->btpo_cycleid == vstate->cycleid)
            {
                opaque->btpo_cycleid = 0;
                MarkBufferDirtyHint(buf, true);
            }
        }
 
        /*
         * If the leaf page is now empty, try to delete it; else count the
         * live tuples (live table TIDs in posting lists are counted as
         * separate live tuples).  We don't delete when backtracking, though,
         * since that would require teaching _bt_pagedel() about backtracking
         * (doesn't seem worth adding more complexity to deal with that).
         *
         * We don't count the number of live TIDs during cleanup-only calls to
         * btvacuumscan (i.e. when callback is not set).  We count the number
         * of index tuples directly instead.  This avoids the expense of
         * directly examining all of the tuples on each page.  VACUUM will
         * treat num_index_tuples as an estimate in cleanup-only case, so it
         * doesn't matter that this underestimates num_index_tuples
         * significantly in some cases.
         */
        if (minoff > maxoff)
            attempt_pagedel = (blkno == scanblkno);
        else if (callback)
            stats->num_index_tuples += nhtidslive;
        else
            stats->num_index_tuples += maxoff - minoff + 1;
 
        Assert(!attempt_pagedel || nhtidslive == 0);
    }
 
    if (attempt_pagedel)
    {
        MemoryContext oldcontext;
 
        /* Run pagedel in a temp context to avoid memory leakage */
        MemoryContextReset(vstate->pagedelcontext);
        oldcontext = MemoryContextSwitchTo(vstate->pagedelcontext);
 
        /*
         * _bt_pagedel maintains the bulk delete stats on our behalf;
         * pages_newly_deleted and pages_deleted are likely to be incremented
         * during call
         */
        Assert(blkno == scanblkno);
        _bt_pagedel(rel, buf, vstate);
 
        MemoryContextSwitchTo(oldcontext);
        /* pagedel released buffer, so we shouldn't */
    }
    else
        _bt_relbuf(rel, buf);
 
    if (backtrack_to != P_NONE)
    {
        blkno = backtrack_to;
        goto backtrack;
    }
}

References _bt_checkpage(), _bt_delitems_vacuum(), _bt_lockbuf(), _bt_pagedel(), _bt_relbuf(), _bt_upgradelockbufcleanup(), Assert, BT_READ, BTP_SPLIT_END, BTPageGetOpaque, BTPageIsRecyclable(), BTPageOpaqueData::btpo_cycleid, BTPageOpaqueData::btpo_flags, BTPageOpaqueData::btpo_next, BTreeTupleGetNPosting(), BTreeTupleIsPivot(), BTreeTupleIsPosting(), btreevacuumposting(), buf, BufferGetPage(), BTVacState::callback, callback(), BTVacState::callback_state, BTVacState::cycleid, ereport, errcode(), errmsg_internal(), IndexVacuumInfo::heaprel, i, IndexVacuumInfo::index, BTVacState::info, LOG, MAIN_FORKNUM, MarkBufferDirtyHint(), MaxIndexTuplesPerPage, MemoryContextReset(), MemoryContextSwitchTo(), IndexBulkDeleteResult::num_index_tuples, OffsetNumberNext, P_FIRSTDATAKEY, P_ISDELETED, P_ISHALFDEAD, P_ISLEAF, P_NONE, P_RIGHTMOST, BTVacState::pagedelcontext, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), PageIsNew(), IndexBulkDeleteResult::pages_deleted, IndexBulkDeleteResult::pages_free, pfree(), RBM_NORMAL, ReadBufferExtended(), RecordFreeIndexPage(), RelationGetRelationName, BTVacState::stats, IndexVacuumInfo::strategy, IndexTupleData::t_tid, IndexBulkDeleteResult::tuples_removed, and vacuum_delay_point().

Referenced by btvacuumscan().

btvacuumscan()

static void btvacuumscan ( IndexVacuumInfo *  info, IndexBulkDeleteResult *  stats, IndexBulkDeleteCallback  callback, void *  callback_state, BTCycleId  cycleid  )

static

Definition at line 926 of file nbtree.c.

{
    Relation    rel = info->index;
    BTVacState  vstate;
    BlockNumber num_pages;
    BlockNumber scanblkno;
    bool        needLock;
 
    /*
     * Reset fields that track information about the entire index now.  This
     * avoids double-counting in the case where a single VACUUM command
     * requires multiple scans of the index.
     *
     * Avoid resetting the tuples_removed and pages_newly_deleted fields here,
     * since they track information about the VACUUM command, and so must last
     * across each call to btvacuumscan().
     *
     * (Note that pages_free is treated as state about the whole index, not
     * the current VACUUM.  This is appropriate because RecordFreeIndexPage()
     * calls are idempotent, and get repeated for the same deleted pages in
     * some scenarios.  The point for us is to track the number of recyclable
     * pages in the index at the end of the VACUUM command.)
     */
    stats->num_pages = 0;
    stats->num_index_tuples = 0;
    stats->pages_deleted = 0;
    stats->pages_free = 0;
 
    /* Set up info to pass down to btvacuumpage */
    vstate.info = info;
    vstate.stats = stats;
    vstate.callback = callback;
    vstate.callback_state = callback_state;
    vstate.cycleid = cycleid;
 
    /* Create a temporary memory context to run _bt_pagedel in */
    vstate.pagedelcontext = AllocSetContextCreate(CurrentMemoryContext,
                                                  "_bt_pagedel",
                                                  ALLOCSET_DEFAULT_SIZES);
 
    /* Initialize vstate fields used by _bt_pendingfsm_finalize */
    vstate.bufsize = 0;
    vstate.maxbufsize = 0;
    vstate.pendingpages = NULL;
    vstate.npendingpages = 0;
    /* Consider applying _bt_pendingfsm_finalize optimization */
    _bt_pendingfsm_init(rel, &vstate, (callback == NULL));
 
    /*
     * The outer loop iterates over all index pages except the metapage, in
     * physical order (we hope the kernel will cooperate in providing
     * read-ahead for speed).  It is critical that we visit all leaf pages,
     * including ones added after we start the scan, else we might fail to
     * delete some deletable tuples.  Hence, we must repeatedly check the
     * relation length.  We must acquire the relation-extension lock while
     * doing so to avoid a race condition: if someone else is extending the
     * relation, there is a window where bufmgr/smgr have created a new
     * all-zero page but it hasn't yet been write-locked by _bt_getbuf(). If
     * we manage to scan such a page here, we'll improperly assume it can be
     * recycled.  Taking the lock synchronizes things enough to prevent a
     * problem: either num_pages won't include the new page, or _bt_getbuf
     * already has write lock on the buffer and it will be fully initialized
     * before we can examine it.  Also, we need not worry if a page is added
     * immediately after we look; the page splitting code already has
     * write-lock on the left page before it adds a right page, so we must
     * already have processed any tuples due to be moved into such a page.
     *
     * XXX: Now that new pages are locked with RBM_ZERO_AND_LOCK, I don't
     * think the use of the extension lock is still required.
     *
     * We can skip locking for new or temp relations, however, since no one
     * else could be accessing them.
     */
    needLock = !RELATION_IS_LOCAL(rel);
 
    scanblkno = BTREE_METAPAGE + 1;
    for (;;)
    {
        /* Get the current relation length */
        if (needLock)
            LockRelationForExtension(rel, ExclusiveLock);
        num_pages = RelationGetNumberOfBlocks(rel);
        if (needLock)
            UnlockRelationForExtension(rel, ExclusiveLock);
 
        if (info->report_progress)
            pgstat_progress_update_param(PROGRESS_SCAN_BLOCKS_TOTAL,
                                         num_pages);
 
        /* Quit if we've scanned the whole relation */
        if (scanblkno >= num_pages)
            break;
        /* Iterate over pages, then loop back to recheck length */
        for (; scanblkno < num_pages; scanblkno++)
        {
            btvacuumpage(&vstate, scanblkno);
            if (info->report_progress)
                pgstat_progress_update_param(PROGRESS_SCAN_BLOCKS_DONE,
                                             scanblkno);
        }
    }
 
    /* Set statistics num_pages field to final size of index */
    stats->num_pages = num_pages;
 
    MemoryContextDelete(vstate.pagedelcontext);
 
    /*
     * If there were any calls to _bt_pagedel() during scan of the index then
     * see if any of the resulting pages can be placed in the FSM now.  When
     * it's not safe we'll have to leave it up to a future VACUUM operation.
     *
     * Finally, if we placed any pages in the FSM (either just now or during
     * the scan), forcibly update the upper-level FSM pages to ensure that
     * searchers can find them.
     */
    _bt_pendingfsm_finalize(rel, &vstate);
    if (stats->pages_free > 0)
        IndexFreeSpaceMapVacuum(rel);
}

References _bt_pendingfsm_finalize(), _bt_pendingfsm_init(), ALLOCSET_DEFAULT_SIZES, AllocSetContextCreate, BTREE_METAPAGE, btvacuumpage(), BTVacState::bufsize, BTVacState::callback, callback(), BTVacState::callback_state, CurrentMemoryContext, BTVacState::cycleid, ExclusiveLock, IndexVacuumInfo::index, IndexFreeSpaceMapVacuum(), BTVacState::info, LockRelationForExtension(), BTVacState::maxbufsize, MemoryContextDelete(), BTVacState::npendingpages, IndexBulkDeleteResult::num_index_tuples, IndexBulkDeleteResult::num_pages, BTVacState::pagedelcontext, IndexBulkDeleteResult::pages_deleted, IndexBulkDeleteResult::pages_free, BTVacState::pendingpages, pgstat_progress_update_param(), PROGRESS_SCAN_BLOCKS_DONE, PROGRESS_SCAN_BLOCKS_TOTAL, RELATION_IS_LOCAL, RelationGetNumberOfBlocks, IndexVacuumInfo::report_progress, BTVacState::stats, and UnlockRelationForExtension().

Referenced by btbulkdelete(), and btvacuumcleanup().